From a3aab0cb48c6bef7385ee5e2af758cc6544011e6 Mon Sep 17 00:00:00 2001
From: Johannes Wienke <languitar@semipol.de>
Date: Sun, 8 Mar 2020 18:26:29 +0100
Subject: [PATCH 1/2] Remove duplicated date parsing test
The exact same tests existed twice in the file.
---
src/paperless_tesseract/tests/test_date.py | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/src/paperless_tesseract/tests/test_date.py b/src/paperless_tesseract/tests/test_date.py
index ac2f9648f..4f931737b 100644
--- a/src/paperless_tesseract/tests/test_date.py
+++ b/src/paperless_tesseract/tests/test_date.py
@@ -172,13 +172,3 @@ class TestDate(TestCase):
document = RasterisedDocumentParser("/dev/null")
document.get_text()
self.assertIsNone(document.get_date())
-
- @mock.patch(
- "paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
- return_value="01-07-0590 00:00:00"
- )
- @mock.patch(MOCK_SCRATCH, SCRATCH)
- def test_crazy_date_past(self, *args):
- document = RasterisedDocumentParser("/dev/null")
- document.get_text()
- self.assertIsNone(document.get_date())
From a311cd498c984d032e53319082871b51d42654e6 Mon Sep 17 00:00:00 2001
From: Johannes Wienke <languitar@semipol.de>
Date: Sun, 8 Mar 2020 18:35:28 +0100
Subject: [PATCH 2/2] Handle dateparser ValueErrors
When parsing dates from the document text or filenames, correctly handle values
errors indicating broken dates. Newly added tests ensure that this handling
works properly.
---
src/documents/parsers.py | 4 ++--
src/paperless_tesseract/tests/test_date.py | 26 ++++++++++++++++++++++
2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/src/documents/parsers.py b/src/documents/parsers.py
index 142ebba68..c0a80a55d 100644
--- a/src/documents/parsers.py
+++ b/src/documents/parsers.py
@@ -108,7 +108,7 @@ class DocumentParser:
try:
date = __parser(date_string, self.FILENAME_DATE_ORDER)
- except TypeError:
+ except (TypeError, ValueError):
# Skip all matches that do not parse to a proper date
continue
@@ -134,7 +134,7 @@ class DocumentParser:
try:
date = __parser(date_string, self.DATE_ORDER)
- except TypeError:
+ except (TypeError, ValueError):
# Skip all matches that do not parse to a proper date
continue
diff --git a/src/paperless_tesseract/tests/test_date.py b/src/paperless_tesseract/tests/test_date.py
index 4f931737b..9e9d48b90 100644
--- a/src/paperless_tesseract/tests/test_date.py
+++ b/src/paperless_tesseract/tests/test_date.py
@@ -172,3 +172,29 @@ class TestDate(TestCase):
document = RasterisedDocumentParser("/dev/null")
document.get_text()
self.assertIsNone(document.get_date())
+
+ @mock.patch(
+ "paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
+ return_value="20 408000l 2475"
+ )
+ @mock.patch(MOCK_SCRATCH, SCRATCH)
+ def test_crazy_date_with_spaces(self, *args):
+ document = RasterisedDocumentParser("/dev/null")
+ document.get_text()
+ self.assertIsNone(document.get_date())
+
+ @mock.patch(
+ "paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
+ return_value="No date in here"
+ )
+ @mock.patch(
+ "paperless_tesseract.parsers.RasterisedDocumentParser."
+ "FILENAME_DATE_ORDER",
+ new_callable=mock.PropertyMock,
+ return_value="YMD"
+ )
+ @mock.patch(MOCK_SCRATCH, SCRATCH)
+ def test_filename_date_parse_invalid(self, *args):
+ document = RasterisedDocumentParser("/tmp/20 408000l 2475 - test.pdf")
+ document.get_text()
+ self.assertIsNone(document.get_date())